What will I get if I subscribe to this Specialization?

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Is financial aid available?

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Adversarial AI: Attacking, Defending & Governing ML Systems

Ce cours n'est pas disponible en Français (France)

Nous sommes actuellement en train de le traduire dans plus de langues.

Adversarial AI: Attacking, Defending & Governing ML Systems

Ce cours fait partie de Spécialisation "AI-Powered Cybersecurity"

Instructeur : Matt Bushby

Inclus avec

5 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Intermédiaire

Expérience recommandée

1 semaine à compléter

à 10 heures par semaine

Planning flexible

Apprenez à votre propre rythme

5 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Intermédiaire

Expérience recommandée

1 semaine à compléter

à 10 heures par semaine

Planning flexible

Apprenez à votre propre rythme

Ce que vous apprendrez

Analyse adversarial attack vectors targeting ML systems including poisoning, model stealing, & backdoor exploits, and assess their operational impact
Design & implement layered technical defences using differential privacy, guardrail protection, & secure algorithm design to maintain model integrity
Plan and conduct AI security testing using red, purple, and blue teaming approaches to validate ML model robustness under adversarial conditions
Evaluate responsible AI governance frameworks and regulatory requirements to ensure AI systems are ethical, fair, and compliant

Détails à connaître

Certificat partageable

Ajouter à votre profil LinkedIn

Récemment mis à jour !

mai 2026

Évaluations

9 affectations¹

Noté par l'IA voir l'avis de non-responsabilité

Enseigné en Anglais

Découvrez comment les employés des entreprises prestigieuses maîtrisent des compétences recherchées

En savoir plus sur Coursera pour les affaires

logos de Petrobras, TATA, Danone, Capgemini, P&G et L'Oreal

Élaborez votre expertise du sujet

Ce cours fait partie de la Spécialisation "AI-Powered Cybersecurity"

Lorsque vous vous inscrivez à ce cours, vous êtes également inscrit(e) à cette Spécialisation.

Apprenez de nouveaux concepts auprès d'experts du secteur
Acquérez une compréhension de base d'un sujet ou d'un outil
Développez des compétences professionnelles avec des projets pratiques
Obtenez un certificat professionnel partageable

Il y a 5 modules dans ce cours

As AI becomes central to cybersecurity defence, attackers are increasingly targeting the AI systems themselves. Model poisoning, adversarial inputs, backdoor exploits, and model stealing are active threats — and most security teams are unprepared to detect or defend against them. This course gives you the knowledge and practical strategies to secure ML systems from the inside out.

You'll examine how ML systems are manipulated through adversarial inputs, poisoning attacks, and threat models across real-world use cases including malware detection and fraud analytics. You'll then explore advanced attack vectors: model poisoning, information leakage, model stealing, and backdoor exploits, and assess their impact on data privacy, intellectual property, and user safety. From attack to defence, you'll learn to apply secure algorithm design, differential privacy, and guardrail protection — and conduct AI security testing using red, purple, and blue teaming approaches. The course closes with AI governance: responsible AI principles, bias mitigation, transparency, data ethics, and the global regulatory frameworks governing AI in cybersecurity. Designed for security analysts, ML engineers, security architects, and risk and compliance professionals working with AI-powered security systems. Job skills taught: Adversarial AI Defence · AI Security Testing · ML Threat Modelling · Model Robustness · Differential Privacy · Red/Blue/Purple Teaming · AI Governance · Responsible AI · Regulatory Compliance for AI Features Coursera Coach, Dialogues and Role Plays - a smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course.

As machine learning integrates into cyber defences, so do methods for breaking it. This module helps you understand how machine learning systems are manipulated and how to defend against it. You will examine adversarial machine learning through examples of threat models, adversarial inputs, and poisoning attacks. Learn how data can compromise models and how attackers exploit vulnerabilities. This module also covers defensive techniques to build resilient models and implement countermeasures. Safeguard your models in malware detection, intrusion systems, or fraud analytics against sophisticated attacks.

Inclus

1 devoir5 plugins

As AI systems deploy, exposure to adversarial threats and misuse increases. This module explores how AI is attacked and exploited, a critical focus for cyber professionals. You will dive into AI-specific attack vectors: model poisoning, information leakage, model stealing, and backdoor exploits. These threats compromise AI performance and pose risks to data privacy, intellectual property, and user safety. Examine harmful AI outputs from biased data or manipulation. Learn how output alignment, ethical censorship, and AI-powered surveillance affect public trust and legal compliance. Analyze case studies to identify AI vulnerabilities and understand societal consequences of insecure deployments. Ensure AI shapes the world securely and responsibly.

Inclus

2 devoirs6 plugins

Defending AI systems against emerging threats is critical. This module explores technical controls and testing strategies to secure AI models. You will learn to apply AI-specific defences, from secure algorithm design to privacy-preserving techniques like differential privacy. Examine how to test and validate AI model robustness using red, purple, and blue teaming approaches. Focus on balancing security, utility, and performance to make informed trade-offs. Gain practical skills to implement trusted controls and rigorously test for resilience against real-world threats, whether building or auditing AI systems.

Inclus

2 devoirs8 plugins

2 devoirsTotal 30 minutes

End of module quiz15 minutes
End of module practice quiz15 minutes

8 pluginsTotal 112 minutes

Overview2 minutes
Introduction10 minutes
Defence techniques and strategies30 minutes
Defences for attacks on GenAI models20 minutes
Selecting appropriate controls15 minutes
Guardrail protection versus guardrail failure15 minutes
AI security testing and benchmarking15 minutes
Summary5 minutes

As AI systems grow, responsible design, deployment, and governance are imperative. This module introduces Responsible AI principles: fairness, bias mitigation, transparency, and ethical accountability. You will explore how AI decisions impact individuals and communities, navigating trade-offs between user privacy, model performance, and transparency. Unpack challenges like data sourcing, labelling, and ethical implications of large-scale models. Learn practical strategies for enhancing trust in AI systems. Dive into global frameworks, policies, and governance models supporting secure, ethical AI adoption. Ensure AI systems are functional, fair, transparent, and aligned with regulatory expectations.

Inclus

2 devoirs6 plugins

In this module, you will analyse a simulated adversarial attack on a deployed ML model, identify the attack type, and recommend a defence strategy. The project allows you to build a comprehensive portfolio artefacts demonstrating your end-to-end capabilities.

Inclus

2 devoirs

Obtenez un certificat professionnel

Ajoutez ce titre à votre profil LinkedIn, à votre curriculum vitae ou à votre CV. Partagez-le sur les médias sociaux et dans votre évaluation des performances.

Instructeur

Matt Bushby

Macquarie University

16 Cours20 698 apprenants

Offert par

Macquarie University

En savoir plus sur Security

Macquarie University
Cyber Incident Response: Triage, Containment & Recovery
Cours
Macquarie University
Machine Learning for Cyber Threat & Anomaly Detection
Cours

Pour quelles raisons les étudiants sur Coursera nous choisissent-ils pour leur carrière ?

Felipe M.

Étudiant(e) depuis 2018

’Pouvoir suivre des cours à mon rythme à été une expérience extraordinaire. Je peux apprendre chaque fois que mon emploi du temps me le permet et en fonction de mon humeur.’

Jennifer J.

Étudiant(e) depuis 2020

’J'ai directement appliqué les concepts et les compétences que j'ai appris de mes cours à un nouveau projet passionnant au travail.’

Larry W.

Étudiant(e) depuis 2021

’Lorsque j'ai besoin de cours sur des sujets que mon université ne propose pas, Coursera est l'un des meilleurs endroits où se rendre.’

Chaitanya A.

’Apprendre, ce n'est pas seulement s'améliorer dans son travail : c'est bien plus que cela. Coursera me permet d'apprendre sans limites.’

Débloquez l'accès à plus de 10 000 cours grâce à un abonnement
Faites progresser votre carrière avec un diplôme en ligne
Obtenez un diplôme auprès d’universités de renommée mondiale - 100 % en ligne
Rejoignez les 4 700 entreprises internationales qui ont choisi Coursera for Business.

Foire Aux Questions

Adversarial machine learning refers to techniques that manipulate, deceive, or exploit AI systems — for example, feeding corrupted training data to degrade model performance, or crafting inputs that cause a model to misclassify a threat. As AI is embedded deeper into security operations, understanding these attack techniques is essential for anyone building, deploying, or auditing AI-powered security tools.

You should have foundational machine learning knowledge and basic cybersecurity awareness before starting this course. Completing the first course in this Specialization — Machine Learning: Cyber Threat & Anomaly Detection — is the best preparation, as this course builds directly on those ML foundations.

Yes. The final module covers responsible AI principles, global governance frameworks, and regulatory compliance requirements — including considerations around fairness, bias, transparency, and data ethics — ensuring you can assess AI deployments against both technical and legal standards.

This course prepares you for roles at the intersection of AI and security — one of the fastest-growing areas in the industry. It is directly relevant to AI Security Engineer, Security Architect, and ML Security Researcher roles, where understanding adversarial attack surfaces and implementing model defences is a core responsibility. Penetration Testers and Red Team Analysts will gain skills in adversarial ML testing and benchmarking. Risk, Compliance, and Governance professionals responsible for overseeing AI deployments will benefit from the responsible AI and regulatory compliance content. It also strengthens the profile of SOC Analysts and Threat Intelligence Analysts who work with or audit AI-powered security tools.

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

Plus de questions

Visitez le Centre d'Aide pour les Étudiants

Aide financière disponible,

¹ Certains travaux de ce cours sont notés par l'IA. Pour ces travaux, vos Données internes seront utilisées conformément à Notification de confidentialité de Coursera.